cs.CL（2024-11-03）

📊 共 11 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models	UniGuard：面向多模态大语言模型越狱攻击的通用安全防护	large language model multimodal
2	Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models	提出REC：通过LLM自动评估生成文本，并提供解释和可验证的引用。	large language model instruction following	✅
3	Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups	评估大型语言模型在多语言多领域复杂词识别任务中的性能	large language model
4	An Exploration of Higher Education Course Evaluation by Large Language Models	利用大型语言模型进行高等教育课程评估探索研究	large language model
5	Graph-based Confidence Calibration for Large Language Models	提出基于图的置信度校准方法，提升大语言模型在关键场景下的可靠性。	large language model
6	High-performance automated abstract screening with large language model ensembles	利用大语言模型集成实现高性能自动化文献摘要筛选	large language model
7	Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors	通过后门攻击检索增强生成系统实现数据提取	large language model instruction following
8	Are LLMs good pragmatic speakers?	利用理性言语行为框架评估大型语言模型（LLMs）的语用能力	large language model
9	LLMs and the Madness of Crowds	研究LLM错误模式，揭示模型间关联性并构建分类体系	large language model
10	Enhancing LLM Evaluations: The Garbling Trick	提出Garbling Trick，增强LLM评估难度，区分模型性能	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Teaching Models to Improve on Tape	提出CORGI：通过强化学习和对话反馈提升LLM在约束条件下的内容生成能力	reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页